Introduction to PyTorch

PyTorch is an open-source machine-learning platform for Python. It is specifically designed for deep learning applications, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs), and it includes extensive layer definitions for these applications. It has built-in tensor operations designed to be used in the same way as NumPy arrays, and they are also optimized to run on GPUs for fast computation. It provides an automatic computational graph scheme so that we won’t need to calculate derivatives by hand.

After a few years of development and improvements, PyTorch now comes with a big package of features and functionalities. Don’t worry about whether we will have to re-learn the tool; even when it is a totally new version, PyTorch has always been good at keeping its core functionality ...